Comparison of multimedia communications QoE models by Bayesian networks and Bayesian statistics: a case study

Abstract

This paper presents a comparison of Bayesian Network (BN) and Bayesian Statistics (BS) modeling for QoE (Quality of Experience) estimation and prediction in multimedia communications, with special attention to prediction. As an example of the comparison, we employ a haptic-audiovisual interactive communication system with guaranteed bandwidth. The QoE measure adopted here is subjects’ overall satisfaction (average score) of performing an interactive task under conditions specified by combinations of the video guaranteed bandwidth, video encoding bit rate, receiver’s playout buffering time and gender of each subject. For BN modeling, we utilize an R package bnlearn and create a discrete BN model of a directed acyclic graph with four nodes corresponding to the four parameters. For BS modeling, we build (1) a Bayesian hierarchical regression model with covariates of the four parameters and random effect terms reflecting users’ individualities and gender, and (2) a Bayesian regression model without the random effect terms. The two BS models are analyzed by Markov chain Monte Carlo (MCMC) simulation with the software OpenBUGS. We then find that the BN and BS models provide approximately the same estimates of the QoE measure. Regarding the prediction, however, the BS model with random effect terms outperforms the BN model and BS model without random effect terms. We thus learn that the random effect terms enhance the ability of Bayesian approaches in QoE prediction.